{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/training-meta-surrogate-model-for","title":"Training Meta-Surrogate Model for Transferable Adversarial Attack","arxiv_id":"2109.01983","date":"2021-09-05","proceeding":null,"authors":["Yunxiao Qin","Yuanhao Xiong","JinFeng Yi","Cho-Jui Hsieh"],"abstract":"We consider adversarial attacks to a black-box model when no queries are allowed. In this setting, many methods directly attack surrogate models and transfer the obtained adversarial examples to fool the target model. Plenty of previous works investigated what kind of attacks to the surrogate model can generate more transferable adversarial examples, but their performances are still limited due to the mismatches between surrogate models and the target model. In this paper, we tackle this problem from a novel angle -- instead of using the original surrogate models, can we obtain a Meta-Surrogate Model (MSM) such that attacks to this model can be easier transferred to other models? We show that this goal can be mathematically formulated as a well-posed (bi-level-like) optimization problem and design a differentiable attacker to make training feasible. Given one or a set of surrogate models, our method can thus obtain an MSM such that adversarial examples generated on MSM enjoy eximious transferability. Comprehensive experiments on Cifar-10 and ImageNet demonstrate that by attacking the MSM, we can obtain stronger transferable adversarial examples to fool black-box models including adversarially trained ones, with much higher success rates than existing methods. The proposed method reveals significant security challenges of deep models and is promising to be served as a state-of-the-art benchmark for evaluating the robustness of deep models in the black-box setting.","url_abs":"https://arxiv.org/abs/2109.01983v2","url_pdf":"https://arxiv.org/pdf/2109.01983v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"training-meta-surrogate-model-for","repo_url":"https://github.com/Trustworthy-AI-Group/TransferAttack","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"training-meta-surrogate-model-for","repo_url":"https://github.com/ydc123/Meta_Surrogate_Model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"adversarial-attack","task_name":"Adversarial Attack"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.01983","atlas_url":"https://app.syntology.ai/?focus=2109.01983","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2109.01983"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2109.01983\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2109.01983"},"call":"get_concepts_for_paper(arxiv_id=\"2109.01983\")"}],"by_repo":[{"repo":"Trustworthy-AI-Group/TransferAttack","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":13,"harvested_for":["2002.05990","2102.00436","2103.15571","2106.04169","2107.14185","2203.09123","2204.00008","2207.05382","2210.05968","2303.15754","2304.13410","2306.05225","2309.14700"],"harvested_for_calls":[{"arxiv_id":"2002.05990","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2002.05990"},"call":"get_harvested_code_for_paper(arxiv_id=\"2002.05990\")"},{"arxiv_id":"2102.00436","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.00436"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.00436\")"},{"arxiv_id":"2103.15571","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.15571"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.15571\")"},{"arxiv_id":"2106.04169","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.04169"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.04169\")"},{"arxiv_id":"2107.14185","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2107.14185"},"call":"get_harvested_code_for_paper(arxiv_id=\"2107.14185\")"},{"arxiv_id":"2203.09123","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.09123"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.09123\")"},{"arxiv_id":"2204.00008","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2204.00008"},"call":"get_harvested_code_for_paper(arxiv_id=\"2204.00008\")"},{"arxiv_id":"2207.05382","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2207.05382"},"call":"get_harvested_code_for_paper(arxiv_id=\"2207.05382\")"},{"arxiv_id":"2210.05968","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2210.05968"},"call":"get_harvested_code_for_paper(arxiv_id=\"2210.05968\")"},{"arxiv_id":"2303.15754","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.15754"},"call":"get_harvested_code_for_paper(arxiv_id=\"2303.15754\")"},{"arxiv_id":"2304.13410","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.13410"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.13410\")"},{"arxiv_id":"2306.05225","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.05225"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.05225\")"},{"arxiv_id":"2309.14700","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.14700"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.14700\")"}]},{"repo":"ydc123/Meta_Surrogate_Model","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4ba9f0feae2053d4941e142546e39ee3b7d8b352ddd084970e9c1629aa1f5dcc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}